© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 16683
    Prev
    Next
    INDEX
    Explanations

    CSS code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Jord
    -0.09
     хват
    -0.08
     shortage
    -0.08
     недостат
    -0.08
    খ
    -0.08
     여행
    -0.08
     täglich
    -0.07
     täg
    -0.07
    জ
    -0.07
     бич
    -0.07
    POSITIVE LOGITS
     relaxed
    0.09
     transitioned
    0.09
     eased
    0.09
     triggered
    0.08
     delayed
    0.08
    -animation
    0.08
    trigger
    0.08
     panels
    0.07
     Romance
    0.07
     accessing
    0.07
    Activations Density 0.002%

    No Known Activations